mihirp1998 / AlignPropLinks
AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
☆299Updated 11 months ago
Alternatives and similar repositories for AlignProp
Users that are interested in AlignProp are comparing it to the libraries listed below
Sorting:
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆240Updated last year
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆589Updated 8 months ago
- [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization☆157Updated 2 weeks ago
- VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation☆320Updated 6 months ago
- Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024☆349Updated last year
- [CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization☆252Updated 5 months ago
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope…☆302Updated 6 months ago
- (CVPR 2024) 🧩 TokenCompose: Text-to-Image Diffusion with Token-level Supervision☆131Updated 9 months ago
- [Neurips 2023 & TPAMI] T2I-CompBench (++) for Compositional Text-to-image Generation Evaluation☆293Updated last month
- GenEval: An object-focused framework for evaluating text-to-image alignment☆369Updated 7 months ago
- RichHF-18K dataset contains rich human feedback labels we collected for our CVPR'24 paper: https://arxiv.org/pdf/2312.10240, along with t…☆140Updated last year
- Better Aligning Text-to-Image Models with Human Preference. ICCV 2023☆290Updated 2 years ago
- Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".☆295Updated last month
- SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training☆183Updated 8 months ago
- 🔥 [CVPR2024] Official implementation of "Self-correcting LLM-controlled Diffusion Models (SLD)☆183Updated last year
- The official implementation of Diffusion-KTO: Aligning Diffusion Models by Optimizing Human Utility☆65Updated last month
- [NeurIPS 2024] CV-VAE: A Compatible Video VAE for Latent Generative Video Models☆282Updated 10 months ago
- A one-stop library to standardize the inference and evaluation of all the conditional image generation models. [ICLR 2024]☆170Updated this week
- [ICLR 2025] Rectified Diffusion: Straightness Is Not Your Need☆238Updated 6 months ago
- Official codebase for the Paper “Retrieval-Augmented Diffusion Models”☆136Updated 2 years ago
- MoVQGAN - model for the image encoding and reconstruction☆251Updated last year
- official repo for "VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation" [EMNLP2024]☆100Updated 7 months ago
- Official pytorch implementation of the paper: "An Edit Friendly DDPM Noise Space: Inversion and Manipulations". CVPR 2024.☆348Updated last year
- [WACV 2024] Training-Free Layout Control with Cross-Attention Guidance☆261Updated last year
- [ICCV 2023] Efficient Diffusion Training via Min-SNR Weighting Strategy☆260Updated 9 months ago
- ☆549Updated 9 months ago
- ☆130Updated last year
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis☆589Updated last year
- [ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers☆349Updated 2 months ago
- My Implementation of Adversarial Diffusion Distillation https://arxiv.org/pdf/2311.17042.pdf☆86Updated 10 months ago